Feb 12, 2020

Predicting sporadic Alzheimer's disease progression via inherited Alzheimer's disease-informed machine-learning

Alzheimer's & Dementia : the Journal of the Alzheimer's Association
Nicolai FranzmeierMichael Ewers

Abstract

Developing cross-validated multi-biomarker models for the prediction of the rate of cognitive decline in Alzheimer's disease (AD) is a critical yet unmet clinical challenge. We applied support vector regression to AD biomarkers derived from cerebrospinal fluid, structural magnetic resonance imaging (MRI), amyloid-PET and fluorodeoxyglucose positron-emission tomography (FDG-PET) to predict rates of cognitive decline. Prediction models were trained in autosomal-dominant Alzheimer's disease (ADAD, n = 121) and subsequently cross-validated in sporadic prodromal AD (n = 216). The sample size needed to detect treatment effects when using model-based risk enrichment was estimated. A model combining all biomarker modalities and established in ADAD predicted the 4-year rate of decline in global cognition (R2 = 24%) and memory (R2 = 25%) in sporadic AD. Model-based risk-enrichment reduced the sample size required for detecting simulated intervention effects by 50%-75%. Our independently validated machine-learning model predicted cognitive decline in sporadic prodromal AD and may substantially reduce sample size needed in clinical trials in AD.

  • References46
  • Citations

References

  • References46
  • Citations

Citations

  • This paper may not have been cited yet.

Mentioned in this Paper

Cerebrospinal Fluid
Cross Validation
Magnetic Resonance Imaging
Structure
SMUG1
Memory
Biological Markers
Positron-Emission Tomography
Fluorodeoxyglucose F18
Cognition

Related Feeds

Alzheimer's Disease: Tau & TDP-43

Alzheimer's disease is a chronic neurodegenerative disease. This feed focuses on the underlying role of Tau proteins and TAR DNA-binding protein 43, as well as other genetic factors, in Alzheimer's.

Alzheimer's Disease: Genetics

Alzheimer's disease is a chronic neurodegenerative disease. Discover genetic and epigenetic aspects of Alzheimer’s disease, including genetic markers and genomic structural variations here.

Alzheimer's Disease: RNA Sequencing

RNA sequencing is used to reveal the presence and quantity of RNA in a given sample. In this feed, RNA sequencing investigates the genetic and molecular mechanisms related to the pathophysiology of Alzheimer's disease (AD). Here are the latest discoveries pertaining to RNA sequencing and this disease.

Alzheimer's Disease: Early Markers

Alzheimer's disease is a chronic neurodegenerative disease. This feed focuses on early markers, as well as environmental, pharmacological, and drug-response biomarkers associated with this disease.

Alzheimer's Disease: Neuroimaging

Alzheimer's disease (AD) is a chronic neurodegenerative disease. Here is the latest research on neuroimaging modalities, including magnetic resonance imaging and positron emission tomography, in AD.

CZI Neurodegeneration Challenge Network

The Neurodegeneration Challenge Network aims to provide funding for and to bring together researchers studying neurodegenerative diseases. Find the latest research from the NDCN grantees here.

CSF & Lymphatic System

This feed focuses on Cerebral Spinal Fluid (CSF) and the lymphatic system. Discover the latest papers using imaging techniques to track CSF outflow into the lymphatic system in animal models.

Related Papers

Frontiers in Bioscience (Landmark Edition)
Can ShengYing Han
© 2020 Meta ULC. All rights reserved